A Survey of Recommendation Algorithms Based on Knowledge Graph Embedding
Чан Лю, Lun Li, Xiaolu Yao, Lin Tang · 2019
Recommender system is able to realize personalized information filtering, which is a key way for knowledge discovering in information-rich environment. Knowledge graphs contain rich semantic associations between entities, which can be utilized to strengthen relationships between recommended items and bring interpretability for recommendation. With the establishment of knowledge graphs in various fields, the increasing numbers of researchers have carried out studies on recommendation algorithm based on knowledge graphs. Among them, recommendation algorithm based on knowledge graph embedding is a kind of simple and effective way to introduce knowledge entities and their relation into traditional recommender system. In this paper, the study about this kind of studies is summarized by analysis of existing literatures. We discuss and compare several studies, and the key elements of these algorithms are statistically analyzed.